An End-to-End Network for Co-Saliency Detection in One Single Image
Abstract
Co-saliency detection within a single image is a common vision problem that has received little attention and has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions are firstly detected using visual primitives such as color and shape and then grouped and merged into a co-saliency map. However, co-saliency is intrinsically perceived complexly with bottom-up and top-down strategies combined in human vision. To address this problem, this study proposes a novel end-to-end trainable network comprising a backbone net and two branch nets. The backbone net uses ground-truth masks as top-down guidance for saliency prediction, whereas the two branch nets construct triplet proposals for regional feature mapping and clustering, which drives the network to be bottom-up sensitive to co-salient regions. We construct a new dataset of 2,019 natural images with co-saliency in each image to evaluate the proposed method. Experimental results show that the proposed method achieves state-of-the-art accuracy with a running speed of 28 fps.
- Publication:
-
arXiv e-prints
- Pub Date:
- October 2019
- DOI:
- 10.48550/arXiv.1910.11819
- arXiv:
- arXiv:1910.11819
- Bibcode:
- 2019arXiv191011819Y
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition
- E-Print:
- SCIENCE CHINA Information Sciences, 2023